EUVIMEDEUVIMED entdecken
Crossref

Beyond imitation: A generate-and-evaluate framework with spatiotemporal risk assessment for end-to-end motion planning

Ying Liu, Yi Liu, Xuewu Lin, Chaoyi Chen, Fang Zhang, Jianqiang Wang

Tsinghua Science and Technology · 18.11.2026

DOI: 10.26599/tst.2026.9010104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tsinghua Science and Technology, online erschienen am 18.11.2026. Verfasst von Ying Liu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

End-to-end motion planning for autonomous vehicles is a critical research frontier, yet prevailing imitation learning approaches are fundamentally constrained by their reliance on regressing to a single, often sub-optimal, ground-truth trajectory. This paradigm fails to address the inherent multi-modality of driving scenarios and the interactive nature of traffic, limiting the system’s ability to discover safer or more efficient behaviors. To address these limitations, we propose a novel “generate-and-evaluate” framework for end-to-end motion planning that moves beyond direct imitation. The framework uses the sparse perception and multi-modal candidate-generation foundation of SparseDrive. Its ego-centric prediction module incorporates observed ego-vehicle, surrounding-agent, map, and temporal context. Subsequently, a principled trajectory selection methodology evaluates these candidates by constructing a predictive spatiotemporal risk field and utilizing a holistic cost function that synthesizes safety, efficiency, and comfort. A core innovation is a time-weighted safety metric that enables a more nuanced and proactive risk assessment. Experimental results show lower collision rate and longitudinal acceleration RMS on mini_val than SparseDrive, with nearly unchanged aver-age speed. On val, higher average speed and lower acceleration RMS come with a higher collision rate, indicating a trade-off among the evaluated criteria.

Zitieren

APA

Liu, Y., Liu, Y., Lin, X., Chen, C., Zhang, F., & Wang, J. (2026). Beyond imitation: A generate-and-evaluate framework with spatiotemporal risk assessment for end-to-end motion planning. Tsinghua Science and Technology. https://doi.org/10.26599/tst.2026.9010104

Vancouver

Liu Y, Liu Y, Lin X, Chen C, Zhang F, Wang J. Beyond imitation: A generate-and-evaluate framework with spatiotemporal risk assessment for end-to-end motion planning. Tsinghua Science and Technology. 2026. doi:10.26599/tst.2026.9010104

BibTeX
@article{Liu2026,
  author = {Liu, Ying and Liu, Yi and Lin, Xuewu and Chen, Chaoyi and Zhang, Fang and Wang, Jianqiang},
  title = {Beyond imitation: A generate-and-evaluate framework with spatiotemporal risk assessment for end-to-end motion planning},
  journal = {Tsinghua Science and Technology},
  year = {2026},
  doi = {10.26599/tst.2026.9010104}
}
Kostenlos starten →